get_activations use multi-input data, does not work.

[uygnef]

Here is the error message

    layer_name='attention_vec')[0], axis=2).squeeze()
  File "/Users/yu/proj/cancel_blame/code/src/lib/attention/attention_utils.py", line 16, in get_activations
    layer_outputs = [func([inputs, 1.])[0] for func in funcs]
  File "/Users/yu/proj/cancel_blame/code/src/lib/attention/attention_utils.py", line 16, in <listcomp>
    layer_outputs = [func([inputs, 1.])[0] for func in funcs]
  File "/anaconda3/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 2666, in __call__
    return self._call(inputs)
  File "/anaconda3/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 2619, in _call
    dtype=tf.as_dtype(tensor.dtype).as_numpy_dtype))
AttributeError: 'list' object has no attribute 'dtype'

[philipperemy]

I removed this code as it is now deprecated. I updated the code reflecting #14.

If you want to get activations, pip install keract from this repo: https://github.com/philipperemy/keract